Delete files encoder.pt encoder_tokens_10k.pt encoder_tokens_10k_metadata.json manifest/split.parquet manifest/data_config.json with huggingface_hub

encoder.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cdb0bd2437c063a79c871eb54445dbee6fb82bd9e20186768fa5b947ffd9d474
-size 79442395

encoder_tokens_10k.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c95bb465bf4a948d8858bcdf51a0ce851e6ba9e849a8db2772fca4f49b14312a
-size 669285010

encoder_tokens_10k_metadata.json

@@ -1,77 +0,0 @@
-{
-  "encoder_checkpoint": "data/encoder/checkpoint/encoder.pt",
-  "coord_scale": 3500.0,
-  "encoder_args": {
-    "v4_config": "data/processed/v4/v4_data_config.json",
-    "v4_normalization": "data/processed/v4/v4_normalization.json",
-    "output_dir": "outputs/encoder_pretrain",
-    "tile_size": 7000.0,
-    "min_tile_points": 200,
-    "max_tile_points": 4096,
-    "tiles_per_batch": 8,
-    "d_model": 256,
-    "num_layers": 6,
-    "num_heads": 8,
-    "dropout": 0.1,
-    "input_length": 294,
-    "mask_ratio": 0.3,
-    "mask_strategy": "block",
-    "sync_mask": true,
-    "mask_schedule": "fixed",
-    "eval_mask_ratio": 0.3,
-    "model_version": "v3_3",
-    "patch_size": 8,
-    "temporal_layers": 2,
-    "temporal_heads": 4,
-    "residual_loss_weight": 1.0,
-    "residual_consistency_weight": 0.1,
-    "residual_head_mode": "additive",
-    "coord_scale": 3500.0,
-    "residual_head_lr": 0.0001,
-    "init_from_checkpoint": null,
-    "point_sampling": "residual_weighted",
-    "residual_sampling_alpha": 0.75,
-    "max_steps": 150000,
-    "duration_hours": null,
-    "lr": 0.0004,
-    "min_lr": 3e-05,
-    "lr_scheduler": "cosine",
-    "scheduler_total_steps": 150000,
-    "warmup_steps": 1000,
-    "weight_decay": 0.01,
-    "precision": "bf16",
-    "device": "cuda:0",
-    "seed": 42,
-    "split_strategy": "random",
-    "val_fraction": 0.1,
-    "test_fraction": 0.1,
-    "stratify_bins": 3,
-    "val_batches": 16,
-    "val_every_steps": 1000,
-    "val_seed": 1729,
-    "checkpoint_every_steps": 5000,
-    "log_every_steps": 200,
-    "train_window_steps": 1000,
-    "resume_from": null
-  },
-  "manifest_path": "data/encoder/manifest/split.parquet",
-  "data_config_path": "data/encoder/manifest/data_config.json",
-  "normalizer_mean": -2.6937686788514412,
-  "normalizer_std": 5.697023090760733,
-  "tile_size": 7000.0,
-  "grid_size": 8,
-  "n_tokens": 65,
-  "n_tiles": 10000,
-  "d_model": 256,
-  "input_length": 294,
-  "time_window_start": 8,
-  "time_window_end": 302,
-  "token_layout": "index 0 = CLS, 1..64 = 8x8 bins row-major",
-  "extraction_script": "src/egms_encoder/extract_tokens.py",
-  "extraction_date_utc": "2026-07-01T00:26:39Z",
-  "bin_occupancy_mean": 0.8588296875,
-  "bin_occupancy_median": 0.9375,
-  "n_points_per_tile_mean": 2018.0485,
-  "n_points_per_tile_min": 200,
-  "n_points_per_tile_max": 4900
-}

manifest/data_config.json

@@ -1,53 +0,0 @@
-{
-  "version": "v4",
-  "created": "2026-05-27",
-  "source": {
-    "tiles_dir": "data/processed/tiles_l3_u_2019_2023_europe",
-    "total_tiles_available": 131281
-  },
-  "filter": {
-    "max_nan_mean": 0.02,
-    "require_first_valid": 0,
-    "require_last_valid_min": 301,
-    "min_points": 200,
-    "pool_size": 83323,
-    "pool_total_points": 101340689
-  },
-  "time_window": {
-    "t_start": 8,
-    "t_end": 302,
-    "input_length": 294,
-    "rationale": "Pool tiles are 100% NaN-free within [t=8, t=302). Earlier steps (t=1,4-7) and tail steps (t=302,303) are systematically missing in 10-21% of pool tiles and are trimmed. Verified by scripts/v4_verify_trim_zero_nan.py on full 83K pool: 0 residual NaN.",
-    "compared_to_v33": "V3.3 used 302 steps (t=0..301 of the no_tail parquet). V4 uses 294 steps (t=8..301 of the raw npz). V4 starts ~6 weeks later in 2019."
-  },
-  "geographic_sampling": {
-    "method": "grid_max_npoints_with_round_robin",
-    "grid_m": 30000,
-    "target_tiles": 10000,
-    "sampled_tiles": 10000,
-    "occupied_cells": 4142,
-    "cells_in_sample": 4142,
-    "rounds_used": 3,
-    "total_points_sampled": 20180485,
-    "seed": 42
-  },
-  "files": {
-    "pool_candidates": "data/processed/v4/v4_pool_candidates.parquet",
-    "sample_10k": "data/processed/v4/v4_sample_10k.parquet",
-    "split": "data/processed/v4/v4_split.json",
-    "nan_profiles_source": "outputs/archive/V4/nan_pattern_analysis_20260527_145457/v4_nan_profiles.parquet"
-  },
-  "split": {
-    "method": "plain_random_tile_level",
-    "ratios": {"train": 0.80, "val": 0.10, "test": 0.10},
-    "counts": {"train": 8000, "val": 1000, "test": 1000},
-    "seed": 1729,
-    "n_grid_cells_per_split": {"train": 4022, "val": 925, "test": 923, "total_cells": 4142},
-    "backup_spatial_blocked": "data/processed/v4/v4_split_spatial_blocked.{json,parquet}.bak"
-  },
-  "tile_field_layout": {
-    "feature_columns_count": 10,
-    "expected_layout": "[easting, northing, height, rmse, mean_velocity, mean_velocity_std, acceleration, acceleration_std, seasonality, seasonality_std, time_series(294)]",
-    "note": "LazyTileStore must construct rows in this order from per-tile npz to remain compatible with V3.3 trainer expectations."
-  }
-}

manifest/split.parquet

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bfb92ef7604d6ab18449f24a10d519985030c87cf6bf380dbc338ed5c3d91784
-size 434406